File size: 2,098 Bytes
ab17dc7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
{
  "best_metric": 0.8404789494013132,
  "best_model_checkpoint": "bert-base-uncased-Research_Articles_Multilabel/checkpoint-6291",
  "epoch": 3.0,
  "global_step": 6291,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9996820855189955e-05,
      "loss": 0.6859,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.2425,
      "step": 2097
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7067238912732475,
      "eval_f1": 0.8347927612375948,
      "eval_loss": 0.19481222331523895,
      "eval_roc_auc": 0.8920854689886804,
      "eval_runtime": 51.1647,
      "eval_samples_per_second": 40.985,
      "eval_steps_per_second": 5.14,
      "step": 2097
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1739,
      "step": 4194
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7072007629947544,
      "eval_f1": 0.83478936128907,
      "eval_loss": 0.1986200213432312,
      "eval_roc_auc": 0.8926225806531218,
      "eval_runtime": 51.1631,
      "eval_samples_per_second": 40.987,
      "eval_steps_per_second": 5.14,
      "step": 4194
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.1328,
      "step": 6291
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7081545064377682,
      "eval_f1": 0.8404789494013132,
      "eval_loss": 0.20385245978832245,
      "eval_roc_auc": 0.897647591573035,
      "eval_runtime": 51.1537,
      "eval_samples_per_second": 40.994,
      "eval_steps_per_second": 5.141,
      "step": 6291
    },
    {
      "epoch": 3.0,
      "step": 6291,
      "total_flos": 5930277461969802.0,
      "train_loss": 0.18313796083265071,
      "train_runtime": 2584.8342,
      "train_samples_per_second": 19.469,
      "train_steps_per_second": 2.434
    }
  ],
  "max_steps": 6291,
  "num_train_epochs": 3,
  "total_flos": 5930277461969802.0,
  "trial_name": null,
  "trial_params": null
}